UvT-WSD1: A cross-lingual word sense disambiguation system


This paper describes the Cross-LingualWord Sense Disambiguation system UvT-WSD1, developed at Tilburg University,for participation in two SemEval-2 tasks:the Cross-Lingual Word Sense Disambiguation task and the Cross-Lingual Lexical Substitution task. The UvT-WSD1system makes use of k-nearest neighbour classifiers, in the form of single-word experts for each target word to be disam-biguated. These classifiers can be constructed using a variety of local and globalcontext features, and these are mapped onto the translations, i.e. the senses,of the words. The system works for a given language-pair, either English-Dutchor English-Spanish in the current implementation, and takes a word-aligned parallel corpus as its input.

SemEval ‘10: Proceedings of the 5th International Workshop on Semantic Evaluation